Muhammad Ahmed

Finetune existing gfpgan_v1 model.

2

Hi, I wanted to finetune the existing GFPGAN model are their any scripts that can be helpful ?

Uploading trained model to Aws Model Registry

3

Hi @rinongal , I have finetuned the styleganNada model and saved it by torch.save(net, "model.pt") but it didn't save the ModelClass with it due to which it is not deploying...

Hi, i wants to add the flagfile into python file so that i dont have to pass commandline arguments to python file any idea how to do it ?

CUDA out of memory

6

Hi @ckkelvinchan , I have tried running inference on RTX2060 with 6gb of vram but it doesn't perform inference on low memory. I tried using video.mp4 as input. Is their...

Training for 7 speakers

1

(Speech separation with Libri7Mix dataset) Hy I have encountered this error while training for 7 speakers. I have created hparam yaml file and added functions in prepare_data.py as well. /speechbrain/speechbrain/utils/data_pipeline.py",...

Minimal Requirements for inference.

2

Hi, I thought it would be useful to install the required packages except of the additional ones. **requirements.txt** ``` dlib gdown scikit-image IPython opencv-python ``` **Commands to setup project** ```...

Inference script for beitv2 pre-trained checkpoint

1

Hi I highly appreciate your work on beitv2. I just wanted to know is there any simple script to run inference on beitv2 model on a single image ?

Colorization uvim model not working

5

Hi @andresusanopinto I hope you are well. I tried using the colorization model on my images but out of 4 it colorized only 1 image and the result is also...

Finetune Paint by example model.

2

Hi @zhangmozhe I would like to know that is there any way to fine-tune the trained paint-by-example model for image accurate image inversion to perform **virtual-try-on** tasks ?

OOM Error due to complete frames processing.

1

Hi @zibojia I am using a video with 60fps of 8 seconds but while processing it is taking all the frames at once. ProPainter has an approach where they process...